
import pandas as pd
import pylab
import matplotlib.pyplot as plt
import numpy as np
import calendar
import seaborn as sns

file_name = 'tmdb_5000_movies.csv'
tmdb_5000 = pd.read_csv(file_name)

pd.set_option('display.max_columns', None)  
pd.set_option('display.max_rows', None)  

pd.set_option('display.float_format', lambda x: '%.2f' % x)
tmdb_5000['release_date'] = pd.to_datetime(tmdb_5000['release_date'], errors='coerce')
main_columns = ['budget','genres','keywords','original_language','original_title','overview','production_companies','production_countries','spoken_languages','tagline','title','revenue','runtime','vote_average','vote_count','popularity','release_date']
tmdb_5000 = tmdb_5000.loc[:, main_columns]


duplicate_rows = tmdb_5000[tmdb_5000.duplicated()]
num_duplicate_rows = len(duplicate_rows)


tmdb_5000['budget'] = tmdb_5000['budget'].replace(0 , np.nan)
tmdb_5000['revenue'] = tmdb_5000['revenue'].replace(0 , np.nan)
tmdb_5000['runtime'] = tmdb_5000['runtime'].replace(0.00 , np.nan)
tmdb_5000['vote_average'] = tmdb_5000['vote_average'].replace(0.00 , np.nan)
tmdb_5000['vote_count'] = tmdb_5000['vote_count'].replace(0 , np.nan)
tmdb_5000['popularity'] = tmdb_5000['popularity'].replace(0.00 , np.nan)
tmdb_5000['release_date'] = tmdb_5000['release_date'].replace(0 , np.nan)


tmdb_5000.sort_values(by='budget', ascending=True)
tmdb_5000 = tmdb_5000[tmdb_5000['budget'] >= 7000]
tmdb_5000.sort_values(by='budget', ascending=True).head()


tmdb_5000.sort_values(by='revenue', ascending=True)
tmdb_5000 = tmdb_5000[tmdb_5000['revenue'] >= 3000]
tmdb_5000.sort_values(by='revenue', ascending=True).head()


tmdb_5000 = tmdb_5000.drop(2384, axis='index')


columns_to_keep = ['budget','revenue','runtime','vote_average','vote_count','popularity','release_date']
sum_stats1 = tmdb_5000.loc[:, columns_to_keep]


test_drop_nulls = pd.DataFrame(tmdb_5000['budget'])
test_drop_nulls = test_drop_nulls.dropna()
print(test_drop_nulls.isnull().sum())

budget    0
dtype: int64


test_drop_nulls
test_drop_nulls2 = pd.concat([test_drop_nulls], ignore_index=True)
test_drop_nulls2.head()


!pip install plotly

Requirement already satisfied: plotly in /Users/ines.delannoy/anaconda3/lib/python3.11/site-packages (5.9.0)
Requirement already satisfied: tenacity>=6.2.0 in /Users/ines.delannoy/anaconda3/lib/python3.11/site-packages (from plotly) (8.2.2)


import ast

# Convert only non-list entries using ast.literal_eval
tmdb_5000['production_countries'] = tmdb_5000['production_countries'].apply(
    lambda x: ast.literal_eval(x) if isinstance(x, str) else x
)

# Extract country names from the list, if present
tmdb_5000['production_countries'] = tmdb_5000['production_countries'].apply(
    lambda x: [i['name'] if isinstance(i, dict) else i for i in x] if isinstance(x, list) and x else x
)


s = tmdb_5000.apply(lambda x: pd.Series(x['production_countries']),axis=1).stack().reset_index(level=1, drop=True)
s.name = 'countries'


con_df = tmdb_5000.drop('production_countries', axis=1).join(s)
con_df = pd.DataFrame(con_df['countries'].value_counts())
con_df['country'] = con_df.index
con_df.columns = ['num_movies', 'country']
con_df = con_df.reset_index(drop=True)
con_df.head(10)


con_df = con_df[con_df['country'] != 'United States of America']


import plotly.graph_objs as go
import plotly.express as px



fig = px.choropleth(
    tmdb_5000,
    locations=con_df['country'],
    locationmode='country names',
    color=con_df['num_movies'],
    title='Movies released per country (excluding US) in The Movie Database 5000',
    color_continuous_scale='viridis'
)

fig.update_layout(
    width=1000,  
    height=800  
)

fig.show()


!jupyter nbconvert --to html "INTERACTIVE PLOT MAP.ipynb"

[NbConvertApp] WARNING | pattern 'INTERACTIVEPLOTMAP.ipynb' matched no files
This application is used to convert notebook files (*.ipynb)
        to various other formats.

        WARNING: THE COMMANDLINE INTERFACE MAY CHANGE IN FUTURE RELEASES.

Options
=======
The options below are convenience aliases to configurable class-options,
as listed in the "Equivalent to" description-line of the aliases.
To see all configurable class-options for some <cmd>, use:
    <cmd> --help-all

--debug
    set log level to logging.DEBUG (maximize logging output)
    Equivalent to: [--Application.log_level=10]
--show-config
    Show the application's configuration (human-readable format)
    Equivalent to: [--Application.show_config=True]
--show-config-json
    Show the application's configuration (json format)
    Equivalent to: [--Application.show_config_json=True]
--generate-config
    generate default config file
    Equivalent to: [--JupyterApp.generate_config=True]
-y
    Answer yes to any questions instead of prompting.
    Equivalent to: [--JupyterApp.answer_yes=True]
--execute
    Execute the notebook prior to export.
    Equivalent to: [--ExecutePreprocessor.enabled=True]
--allow-errors
    Continue notebook execution even if one of the cells throws an error and include the error message in the cell output (the default behaviour is to abort conversion). This flag is only relevant if '--execute' was specified, too.
    Equivalent to: [--ExecutePreprocessor.allow_errors=True]
--stdin
    read a single notebook file from stdin. Write the resulting notebook with default basename 'notebook.*'
    Equivalent to: [--NbConvertApp.from_stdin=True]
--stdout
    Write notebook output to stdout instead of files.
    Equivalent to: [--NbConvertApp.writer_class=StdoutWriter]
--inplace
    Run nbconvert in place, overwriting the existing notebook (only
            relevant when converting to notebook format)
    Equivalent to: [--NbConvertApp.use_output_suffix=False --NbConvertApp.export_format=notebook --FilesWriter.build_directory=]
--clear-output
    Clear output of current file and save in place,
            overwriting the existing notebook.
    Equivalent to: [--NbConvertApp.use_output_suffix=False --NbConvertApp.export_format=notebook --FilesWriter.build_directory= --ClearOutputPreprocessor.enabled=True]
--no-prompt
    Exclude input and output prompts from converted document.
    Equivalent to: [--TemplateExporter.exclude_input_prompt=True --TemplateExporter.exclude_output_prompt=True]
--no-input
    Exclude input cells and output prompts from converted document.
            This mode is ideal for generating code-free reports.
    Equivalent to: [--TemplateExporter.exclude_output_prompt=True --TemplateExporter.exclude_input=True --TemplateExporter.exclude_input_prompt=True]
--allow-chromium-download
    Whether to allow downloading chromium if no suitable version is found on the system.
    Equivalent to: [--WebPDFExporter.allow_chromium_download=True]
--disable-chromium-sandbox
    Disable chromium security sandbox when converting to PDF..
    Equivalent to: [--WebPDFExporter.disable_sandbox=True]
--show-input
    Shows code input. This flag is only useful for dejavu users.
    Equivalent to: [--TemplateExporter.exclude_input=False]
--embed-images
    Embed the images as base64 dataurls in the output. This flag is only useful for the HTML/WebPDF/Slides exports.
    Equivalent to: [--HTMLExporter.embed_images=True]
--sanitize-html
    Whether the HTML in Markdown cells and cell outputs should be sanitized..
    Equivalent to: [--HTMLExporter.sanitize_html=True]
--log-level=<Enum>
    Set the log level by value or name.
    Choices: any of [0, 10, 20, 30, 40, 50, 'DEBUG', 'INFO', 'WARN', 'ERROR', 'CRITICAL']
    Default: 30
    Equivalent to: [--Application.log_level]
--config=<Unicode>
    Full path of a config file.
    Default: ''
    Equivalent to: [--JupyterApp.config_file]
--to=<Unicode>
    The export format to be used, either one of the built-in formats
            ['asciidoc', 'custom', 'html', 'latex', 'markdown', 'notebook', 'pdf', 'python', 'rst', 'script', 'slides', 'webpdf']
            or a dotted object name that represents the import path for an
            ``Exporter`` class
    Default: ''
    Equivalent to: [--NbConvertApp.export_format]
--template=<Unicode>
    Name of the template to use
    Default: ''
    Equivalent to: [--TemplateExporter.template_name]
--template-file=<Unicode>
    Name of the template file to use
    Default: None
    Equivalent to: [--TemplateExporter.template_file]
--theme=<Unicode>
    Template specific theme(e.g. the name of a JupyterLab CSS theme distributed
    as prebuilt extension for the lab template)
    Default: 'light'
    Equivalent to: [--HTMLExporter.theme]
--sanitize_html=<Bool>
    Whether the HTML in Markdown cells and cell outputs should be sanitized.This
    should be set to True by nbviewer or similar tools.
    Default: False
    Equivalent to: [--HTMLExporter.sanitize_html]
--writer=<DottedObjectName>
    Writer class used to write the
                                        results of the conversion
    Default: 'FilesWriter'
    Equivalent to: [--NbConvertApp.writer_class]
--post=<DottedOrNone>
    PostProcessor class used to write the
                                        results of the conversion
    Default: ''
    Equivalent to: [--NbConvertApp.postprocessor_class]
--output=<Unicode>
    overwrite base name use for output files.
                can only be used when converting one notebook at a time.
    Default: ''
    Equivalent to: [--NbConvertApp.output_base]
--output-dir=<Unicode>
    Directory to write output(s) to. Defaults
                                  to output to the directory of each notebook. To recover
                                  previous default behaviour (outputting to the current
                                  working directory) use . as the flag value.
    Default: ''
    Equivalent to: [--FilesWriter.build_directory]
--reveal-prefix=<Unicode>
    The URL prefix for reveal.js (version 3.x).
            This defaults to the reveal CDN, but can be any url pointing to a copy
            of reveal.js.
            For speaker notes to work, this must be a relative path to a local
            copy of reveal.js: e.g., "reveal.js".
            If a relative path is given, it must be a subdirectory of the
            current directory (from which the server is run).
            See the usage documentation
            (https://nbconvert.readthedocs.io/en/latest/usage.html#reveal-js-html-slideshow)
            for more details.
    Default: ''
    Equivalent to: [--SlidesExporter.reveal_url_prefix]
--nbformat=<Enum>
    The nbformat version to write.
            Use this to downgrade notebooks.
    Choices: any of [1, 2, 3, 4]
    Default: 4
    Equivalent to: [--NotebookExporter.nbformat_version]

Examples
--------

    The simplest way to use nbconvert is

            > jupyter nbconvert mynotebook.ipynb --to html

            Options include ['asciidoc', 'custom', 'html', 'latex', 'markdown', 'notebook', 'pdf', 'python', 'rst', 'script', 'slides', 'webpdf'].

            > jupyter nbconvert --to latex mynotebook.ipynb

            Both HTML and LaTeX support multiple output templates. LaTeX includes
            'base', 'article' and 'report'.  HTML includes 'basic', 'lab' and
            'classic'. You can specify the flavor of the format used.

            > jupyter nbconvert --to html --template lab mynotebook.ipynb

            You can also pipe the output to stdout, rather than a file

            > jupyter nbconvert mynotebook.ipynb --stdout

            PDF is generated via latex

            > jupyter nbconvert mynotebook.ipynb --to pdf

            You can get (and serve) a Reveal.js-powered slideshow

            > jupyter nbconvert myslides.ipynb --to slides --post serve

            Multiple notebooks can be given at the command line in a couple of
            different ways:

            > jupyter nbconvert notebook*.ipynb
            > jupyter nbconvert notebook1.ipynb notebook2.ipynb

            or you can specify the notebooks list in a config file, containing::

                c.NbConvertApp.notebooks = ["my_notebook.ipynb"]

            > jupyter nbconvert --config mycfg.py

To see all available configurables, use `--help-all`.

	budget	genres	keywords	original_language	original_title	overview	production_companies	production_countries	spoken_languages	tagline	title	revenue	runtime	vote_average	vote_count	popularity	release_date
4796	7000.00	[{"id": 878, "name": "Science Fiction"}, {"id"...	[{"id": 1448, "name": "distrust"}, {"id": 2101...	en	Primer	Friends/fledgling entrepreneurs invent a devic...	[{"name": "Thinkfilm", "id": 446}]	[{"iso_3166_1": "US", "name": "United States o...	[{"iso_639_1": "en", "name": "English"}]	What happens if it actually works?	Primer	424760.00	77.00	6.90	658.00	23.31	2004-10-08
4696	8000.00	[{"id": 18, "name": "Drama"}, {"id": 10749, "n...	[{"id": 237, "name": "gay"}, {"id": 1025, "nam...	en	Weekend	After a drunken house party with his straight ...	[{"name": "EM Media", "id": 1917}, {"name": "T...	[{"iso_3166_1": "GB", "name": "United Kingdom"}]	[{"iso_639_1": "en", "name": "English"}]	A (sort of) love story between two guys over a...	Weekend	469947.00	96.00	7.40	163.00	1.04	2011-09-22
4799	9000.00	[{"id": 35, "name": "Comedy"}, {"id": 10749, "...	[]	en	Newlyweds	A newlywed couple's honeymoon is upended by th...	[]	[]	[]	A newlywed couple's honeymoon is upended by th...	Newlyweds	NaN	85.00	5.90	5.00	0.64	2011-12-26
4724	10000.00	[{"id": 18, "name": "Drama"}, {"id": 14, "name...	[{"id": 1009, "name": "baby"}, {"id": 1852, "n...	en	Eraserhead	Henry Spencer tries to survive his industrial ...	[{"name": "American Film Institute (AFI)", "id...	[{"iso_3166_1": "US", "name": "United States o...	[{"iso_639_1": "en", "name": "English"}]	Where your nightmares end...	Eraserhead	7000000.00	89.00	7.50	485.00	20.40	1977-03-19
4788	12000.00	[{"id": 27, "name": "Horror"}, {"id": 35, "nam...	[{"id": 237, "name": "gay"}, {"id": 900, "name...	en	Pink Flamingos	Notorious Baltimore criminal and underground f...	[{"name": "Dreamland Productions", "id": 407}]	[{"iso_3166_1": "US", "name": "United States o...	[{"iso_639_1": "en", "name": "English"}]	An exercise in poor taste.	Pink Flamingos	6000000.00	93.00	6.20	110.00	4.55	1972-03-12

	budget	genres	keywords	original_language	original_title	overview	production_companies	production_countries	spoken_languages	tagline	title	revenue	runtime	vote_average	vote_count	popularity	release_date
4065	2100000.00	[{"id": 18, "name": "Drama"}, {"id": 80, "name...	[{"id": 40865, "name": "new york state"}, {"id...	en	Mi America	A hate-crime has been committed in a the small...	[{"name": "Industrial House Films", "id": 65589}]	[{"iso_3166_1": "US", "name": "United States o...	[{"iso_639_1": "es", "name": "Espa\u00f1ol"}, ...	NaN	Mi America	3330.00	126.00	NaN	NaN	0.04	2015-10-16
1999	25000000.00	[{"id": 14, "name": "Fantasy"}, {"id": 12, "na...	[{"id": 212, "name": "london england"}, {"id":...	en	The Adventurer: The Curse of the Midas Box	17-year-old Mariah Mundi's life is turned upsi...	[{"name": "Matador Pictures", "id": 707}, {"na...	[{"iso_3166_1": "BE", "name": "Belgium"}, {"is...	[{"iso_639_1": "en", "name": "English"}]	The new name for adventure.	The Adventurer: The Curse of the Midas Box	6399.00	99.00	5.10	73.00	8.84	2013-12-05
4399	1000000.00	[{"id": 18, "name": "Drama"}, {"id": 14, "name...	[{"id": 3298, "name": "hallucination"}, {"id":...	en	Special	A lonely metermaid has a psychotic reaction to...	[{"name": "Rival Pictures", "id": 2830}]	[{"iso_3166_1": "US", "name": "United States o...	[{"iso_639_1": "en", "name": "English"}]	NaN	Special	7202.00	81.00	6.60	32.00	1.26	2006-01-30
3121	10000000.00	[{"id": 35, "name": "Comedy"}]	[]	en	Janky Promoters	Two shady concert promoters get into hot water...	[{"name": "Cube Vision", "id": 2780}, {"name":...	[{"iso_3166_1": "US", "name": "United States o...	[{"iso_639_1": "en", "name": "English"}]	NaN	Janky Promoters	9069.00	85.00	7.00	5.00	1.73	2009-10-16
4772	31192.00	[{"id": 18, "name": "Drama"}, {"id": 28, "name...	[{"id": 9826, "name": "murder"}, {"id": 10123,...	en	Down Terrace	After serving jail time for a mysterious crime...	[]	[{"iso_3166_1": "GB", "name": "United Kingdom"}]	[{"iso_639_1": "en", "name": "English"}]	You're only as good as the people you know.	Down Terrace	10000.00	89.00	6.30	26.00	1.33	2009-09-01

	budget
0	237000000.00
1	300000000.00
2	245000000.00
3	250000000.00
4	260000000.00

	num_movies	country
0	2895	United States of America
1	431	United Kingdom
2	231	Germany
3	195	France
4	161	Canada
5	77	Australia
6	48	Italy
7	43	Spain
8	40	Japan
9	37	China